© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126131
    Prev
    Next
    INDEX
    Explanations

    terms related to identifiers in programming or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iers
    -0.07
    istry
    -0.07
    kit
    -0.07
    ãĥ¼ãĥį
    -0.07
    rim
    -0.07
    /fixtures
    -0.07
    FX
    -0.07
    eil
    -0.07
    yer
    -0.06
    roe
    -0.06
    POSITIVE LOGITS
    cloak
    0.07
    borg
    0.07
    530
    0.07
    amental
    0.06
    gent
    0.06
    (s
    0.06
    .generated
    0.06
    NewLabel
    0.06
    ERAL
    0.06
    cpy
    0.06
    Activations Density 0.005%

    No Known Activations